Research map / Vision-language and multimodal / Visual question answering
Explicit Reasoning over End-to-End Neural Architectures for Visual Question Answering
Somak Aditya, Yezhou Yang, Chitta Baral
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add PSL reasoning over image and question triplets to the VQA answer prior | trained VQA system · VQA validation, non-Yes/No and non-Counting total | accuracy: 48.49 -> 48.58 | Improved |
| Add PSL reasoning over image and question triplets | trained VQA system · VQA validation, what animal is | accuracy: 65 -> 66.22 | Improved |
| Add PSL reasoning over image and question triplets | trained VQA system · VQA validation, what color is the | accuracy: 62.44 -> 61.39 | Hurt |
| Add ConceptNet 5.5 embeddings to word2vec for phrase similarity (ablation) | PSLDVQ · VQA validation, non-Yes/No and non-Counting total | accuracy: 48.58 -> 48.42 | Hurt |
| Add ConceptNet 5.5 embeddings to word2vec for phrase similarity (ablation) | PSLDVQ · VQA validation, specific question categories: Number | accuracy: 2.58 -> 2.7 | Improved |
| Add ConceptNet 5.5 embeddings to word2vec for phrase similarity (ablation) | PSLDVQ · VQA validation, what animal is | accuracy: 66.22 -> 66.36 | Improved |
| Add ConceptNet 5.5 embeddings to word2vec for phrase similarity (ablation) | PSLDVQ · VQA validation, what color is the | accuracy: 61.39 -> 60.37 | Hurt |
Closest papers by meaning
- Neuro-Symbolic Visual Reasoning: Disentangling "Visual" from "Reasoning" (ICML 2020 · similarity 0.91)
- Visual Question Answering with Question Representation Update (QRU) (NeurIPS 2016 · similarity 0.91)
- TOA: Task-oriented Active VQA (NeurIPS 2023 · similarity 0.91)
- OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge (CVPR 2019 · similarity 0.91)
- StaR-KVQA: Structured Reasoning Traces for Implicit-Knowledge Visual Question Answering (CVPR 2026 · similarity 0.91)
- A-OKVQA: A Benchmark for Visual Question Answering Using World Knowledge (ECCV 2022 · similarity 0.91)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
